CONF hung:MM:2007/IDIAP Using Audio and Video Features to Classify the Most Dominant Person in a Group Meeting Hung, Hayley Jayagopi, Dinesh Babu Yeo, Chuohao Friedland, Gerald Ba, Silèye O. Odobez, Jean-Marc Ramchandran, Kannan Mirghafori, Nikki Gatica-Perez, Daniel EXTERNAL http://publications.idiap.ch/attachments/papers/2007/hung-MM-2007.pdf PUBLIC http://publications.idiap.ch/index.php/publications/showcite/hung:rr07-29 Related documents "" 2007 IDIAP-RR 07-29 The automated extraction of semantically meaningful information from multi-modal data is becoming increasingly necessary due to the escalation of captured data for archival. A novel area of multi-modal data labelling, which has received relatively little attention, is the automatic estimation of the most dominant person in a group meeting. In this paper, we provide a framework for detecting dominance in group meetings using different audio and video cues. We show that by using a simple model for dominance estimation we can obtain promising results. REPORT hung:rr07-29/IDIAP Using Audio and Video Features to Classify the Most Dominant Person in a Group Meeting Hung, Hayley Jayagopi, Dinesh Babu Yeo, Chuohao Friedland, Gerald Ba, Silèye O. Odobez, Jean-Marc Ramchandran, Kannan Mirghafori, Nikki Gatica-Perez, Daniel EXTERNAL http://publications.idiap.ch/attachments/reports/2007/hung-idiap-rr-07-29.pdf PUBLIC Idiap-RR-29-2007 2007 IDIAP To appear in Association for Computing Machinery - Multimedia (ACM-MM,',','), September 23--28, 2007, Augsburg, Bavaria, Germany. The automated extraction of semantically meaningful information from multi-modal data is becoming increasingly necessary due to the escalation of captured data for archival. A novel area of multi-modal data labelling, which has received relatively little attention, is the automatic estimation of the most dominant person in a group meeting. In this paper, we provide a framework for detecting dominance in group meetings using different audio and video cues. We show that by using a simple model for dominance estimation we can obtain promising results.